Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/kirodotdev/kirocrew/web-browsenpx skills add kirodotdev/KiroCrew --skill web-browsegit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kirodotdev/kirocrew/web-browse)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/web-browse"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/web-browse.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00093 | $0.02397 |
| Opus 5 | $0.00046 | $0.01198 |
| Sonnet 5 | $0.00019 | $0.00479 |
| Haiku 4.5 | $0.00009 | $0.00240 |
Grade A, and why
web-browse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Browse: open a real page for the user to look at
Your PRIMARY way to open a page in the dashboard's Browser panel is the
browser MCP tool — it drives the built-in Electron panel in-process, with
no separate Chromium and no macOS security prompt:
browser(op="navigate", args={"url": "https://example.com"})
Other ops: snapshot (get element refs), then click / type / press_key /
hover / select_option / screenshot / wait_for / back / console. Call
snapshot first to get refs before a click/type.
If the tool returns guidance that no native panel is serving this session (a
remote gateway, or a plain-browser dashboard with no Electron panel), THEN fall
back to playwright-cli (below). Do not reach for playwright-cli first: on the
desktop app it spawns its own unsigned Chromium and triggers a macOS security
prompt, and the user is watching the built-in panel, not that window.
Fallback (and attach / logged-in sessions): playwright-cli
The dashboard's right-side Browser panel also shows a live playwright-cli
session. When the browser tool reports no native panel — or you need an
attached browser carrying the user's real logins — open a page with:
playwright-cli open https://example.com
The page loads in the session, the panel surfaces it, and the command prints the page URL, the page title, and a path to a snapshot YAML.
This is the view path. It is deliberately narrow: open the URL and show it, nothing more.
What you get back, and what to do with it
One command prints roughly three lines. That is usually the whole answer for this skill: the URL and title confirm the page loaded, so you do not need the snapshot at all.
- Open the snapshot YAML only when you need the tree (you are about to click something, or the user asked what is on the page). Read it with your own file tools, at the exact path printed. Do not guess a path.
- You do not need a screenshot to make the page appear.
openalone shows it. Screenshot only when you need to inspect the rendering, which is theweb-verifyskill's job. - A screenshot is not what the user sees. They are watching the live session.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 195 lines · 93 tokens per session scan A 4b1ab364fea4
web-browse is a skill published in the GitHub repository kirodotdev/KiroCrew (3,646 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 2,397 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.
creating-actions
This skill should be used when the user asks to "create an action", "save this flow as an action", "make this replayable", "record a reusable action", "author a Maestro flow as an action", "add a login/setup action", or when a verified UI walk should be persisted under .rn-agent/actions/ so future sessions can replay…
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…